BARE：面向偏见意识和推理增强的单塔视觉定位
BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding
AI总结：
BARE通过引入三个新模块，提升单塔视觉定位任务中对偏见的意识和推理能力，实现更高效和准确的多模态理解。
摘要：
视觉定位（VG），旨在定位由表达式所指的具体区域，是多模态理解领域中的基础但具有挑战性的任务。尽管最近的接地转移工作通过单塔架构推动了该领域的发展，但仍然存在两个主要限制：（1）过于纠缠的多模态表示加剧了欺骗性模态偏见，（2）不足的语义推理阻碍了对指代线索的理解。在本文中，我们提出了BARE，一种用于单塔视觉定位的偏见意识和推理增强框架。BARE引入了一种机制，通过三个新的模块保留模态特定的特征并构建指代语义：（i）语言显著性调节器，（ii）视觉偏见校正和（iii）指代关系增强，这些模块共同缓解多模态干扰并增强指代理解。在五个基准上的广泛实验结果表明，BARE不仅实现了最先进的性能，还比现有方法提供了更优越的计算效率。代码已公开在https://github.com/Marloweeee/BARE。
英文摘要：
Visual Grounding (VG), which aims to locate a specific region referred to by expressions, is a fundamental yet challenging task in the multimodal understanding fields. While recent grounding transfer works have advanced the field through one-tower architectures, they still suffer from two primary limitations: (1) over-entangled multimodal representations that exacerbate deceptive modality biases, and (2) insufficient semantic reasoning that hinders the comprehension of referential cues. In this paper, we propose BARE, a bias-aware and reasoning-enhanced framework for one-tower visual grounding. BARE introduces a mechanism that preserves modality-specific features and constructs referential semantics through three novel modules: (i) language salience modulator, (ii) visual bias correction and (iii) referential relationship enhancement, which jointly mitigate multimodal distractions and enhance referential comprehension. Extensive experimental results on five benchmarks demonstrate that BARE not only achieves state-of-the-art performance but also delivers superior computational efficiency compared to existing approaches. The code is publicly accessible at https://github.com/Marloweeee/BARE.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
